vllm-flash-attn3
replicate/vllm-flash-attn3
kernelsLicense: apache-2.0
Tracked by OpenModelStats since September 15, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 10K
- Total downloadsCumulative all-time download counter reported by the source platform.
- 10K
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +169(increase)
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 0
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads.
- #8,334
- 166(up 166 places)this week
- Parameters
- —
- Last source update
- Sep 1, 2026
- vllm-flash-attn3 gained 169 downloads during the last seven tracked days.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
vllm-flash-attn3 is an AI model published by replicate. OpenModelStats has tracked the model since Sep 15, 2026, most recently observing it 13h ago.
- Published
- Oct 1, 2026
- Last updated
- Sep 1, 2026
- Library
- kernels
- License
- apache-2.0
- Task
- —
- Parameters
- —
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 24
kernelslicense:apache-2.0region:us
Publisher
replicateView publisher statistics →Similar models
| Model | DL 30D |
|---|---|
| all-MiniLM-L6-v2sentence-transformers | 228M |
| ms-marco-MiniLM-L6-v2cross-encoder | 81M |
| bge-small-en-v1.5BAAI | 60.9M |
| paraphrase-multilingual-MiniLM-L12-v2sentence-transformers | 49.2M |
| electra-base-discriminatorgoogle | 45.3M |
| bert-base-uncasedgoogle-bert | 36.7M |